FoldNet++: a Large-Scale Synthetic Dataset for Robotic T-Shirt Folding and Unfolding

• URL: http://arxiv.org/abs/2609.12433v1
• Date: Fri, 11 Sep 2026 04:43:48 GMT
• Title: FoldNet++: a Large-Scale Synthetic Dataset for Robotic T-Shirt Folding and Unfolding
• Abstract summary: We present a large-scale synthetic dataset for robotic T-shirt folding and unfolding.<n>We generate manipulation demonstrations for different robotic embodiments through a unified rule-based framework.<n>We use these demonstrations to train visuomotor policies, and experimental results demonstrate that models trained solely on our synthetic data can achieve over 90% end-to-end task success rates.
• Score: 10.983573449935447
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to the highly deformable nature of garments, training a generalizable policy for robotic T-shirt folding and unfolding remains a significant challenge. In this work, we present a large-scale synthetic dataset for robotic T-shirt folding and unfolding, covering 6 robotic embodiments, 1K T-shirts, 1K environmental assets, and 120K episodes with rich annotations, which can be used to train a wide range of manipulation policies. We first follow the FoldNet pipeline to generate a large-scale dataset of physically simulatable T-shirts with diverse appearances and annotated semantic keypoints. Based on these semantic keypoints, we then generate manipulation demonstrations for different robotic embodiments through a unified rule-based framework. We use these demonstrations to train visuomotor policies, and experimental results demonstrate that models trained solely on our synthetic data can achieve over 90\% end-to-end task success rates when directly deployed to unseen real-world environments and previously unseen T-shirts from arbitrary initial configurations. Project URL: https://pku-epic.github.io/FoldNetXX/.

Related papers

• Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors [15.482859998546985]
  We study whether a world-action model can be trained from synthetic priors and deployed zero-shot in the real world.<n>We construct simulation environments with extensive domain randomization and generate demonstrations using the AnyTask motion planning pipeline.<n>When deployed zero-shot on a Franka Robot, our policy attains a 35% average success rate.
  arXiv  Detail & Related papers  (2026-06-30T03:49:31Z)
• UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data [70.96218513410454]
  We introduce UltraDexGrasp, a framework for universal dexterous grasping with bimanual robots.<n>The proposed data-generation pipeline integrates optimization-based grasp synthesis with planning-based demonstration generation.<n>Based on UltraDexGrasp-20M, we develop a simple yet effective grasp policy that takes point clouds as input, aggregates scene features via unidirectional attention, and predicts control commands.
  arXiv  Detail & Related papers  (2026-03-05T15:54:21Z)
• Large Video Planner Enables Generalizable Robot Control [117.49024534548319]
  General-purpose robots require decision-making models that generalize across diverse tasks and environments.<n>Recent works build robot foundation models by extending multimodal large language models (LMs) with action outputs, creating vision--action (VLA) systems.<n>We explore an alternative paradigm of using large-scale video pretraining as a primary modality for building robot foundation models.
  arXiv  Detail & Related papers  (2025-12-17T18:35:54Z)
• FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis [9.22657317122778]
  We present a synthetic garment dataset that can be used for robotic garment folding.<n>We generate folding demonstrations in simulation and train folding policies via closed-loop imitation learning.<n> KG-DAgger significantly improves the model performance, boosting the real-world success rate by 25%.
  arXiv  Detail & Related papers  (2025-05-14T03:34:30Z)
• Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models [53.22792173053473]
  We introduce an interactive robotic manipulation framework called Polaris. Polaris integrates perception and interaction by utilizing GPT-4 alongside grounded vision models. We propose a novel Synthetic-to-Real (Syn2Real) pose estimation pipeline.
  arXiv  Detail & Related papers  (2024-08-15T06:40:38Z)
• UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Folding [53.38503172679482]
  UniFolding is a sample-efficient, scalable, and generalizable robotic system for unfolding and folding garments. UniFolding employs the proposed UFONet neural network to integrate unfolding and folding decisions into a single policy model. The system is tested on two garment types: long-sleeve and short-sleeve shirts.
  arXiv  Detail & Related papers  (2023-11-02T14:25:10Z)
• Robot Learning with Sensorimotor Pre-training [98.7755895548928]
  We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. We find that sensorimotor pre-training consistently outperforms training from scratch, has favorable scaling properties, and enables transfer across different tasks, environments, and robots.
  arXiv  Detail & Related papers  (2023-06-16T17:58:10Z)
• Imitating Task and Motion Planning with Visuomotor Transformers [71.41938181838124]
  Task and Motion Planning (TAMP) can autonomously generate large-scale datasets of diverse demonstrations. In this work, we show that the combination of large-scale datasets generated by TAMP supervisors and flexible Transformer models to fit them is a powerful paradigm for robot manipulation. We present a novel imitation learning system called OPTIMUS that trains large-scale visuomotor Transformer policies by imitating a TAMP agent.
  arXiv  Detail & Related papers  (2023-05-25T17:58:14Z)
• Learning Fabric Manipulation in the Real World with Human Videos [10.608723220309678]
  Fabric manipulation is a long-standing challenge in robotics due to the enormous state space and complex dynamics. Most prior methods rely heavily on simulation, which is still limited by the large sim-to-real gap of deformable objects. A promising alternative is to learn fabric manipulation directly from watching humans perform the task.
  arXiv  Detail & Related papers  (2022-11-05T07:09:15Z)
• From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data [18.041329181385414]
  Conditional Behavior Transformers (C-BeT) is a method that combines the multi-modal generation ability of Behavior Transformer with future-conditioned goal specification. C-BeT improves upon prior state-of-the-art work in learning from play data by an average of 45.7%. We demonstrate for the first time that useful task-centric behaviors can be learned on a real-world robot purely from play data.
  arXiv  Detail & Related papers  (2022-10-18T17:59:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.